INDEX

Explanations

the letter 'F' in various contexts and forms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 occasion

-0.15

estre

-0.15

 Guard

-0.15

alion

-0.15

çª

-0.14

okit

-0.14

andin

-0.14

interop

-0.14

ocab

-0.14

POSITIVE LOGITS

eds

0.37

BI

0.31

bi

0.29

ederal

0.28

ISA

0.26

raud

0.25

entanyl

0.25

Bi

0.22

Bi

0.22

elon

0.22

Activations Density 0.027%

the letter 'F' in various contexts and forms

No Comments

No Known Activations